Tool Poisoning Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 11 Oct 2026.
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
What the code does
We read the source, 5 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const result = spawnSync(process.execPath, [cliPath, entry.cmd, ...args], {
pattern: /\b(?:read|cat|include|attach|append)\b[^.]{0,80}(?:\.ssh\b|\bid_rsa\b|\.env\b|\.aws[\\/]credentials\b|\bprivate[\s_-]?key\b|\.npmrc\b)/i,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Tool Poisoning Scanner
same job, measured the same wayScans MCP tool definitions for hidden instructions and confused-deputy sinks
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Score text and web pages for signs of AI writing; check images for hidden AI instructions.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Security scanner for MCP servers - detects tool poisoning and injection
Memory for coding conventions and standing instructions that persists across sessions.
Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
Tool Poisoning Scanner — questions
Answers built from our own checks of this server.